Deep Neural Networks (DNNs) have been deployed in many real-world applications in various domains, both industry and academic, and have proven to deliver outstanding performance. However, DNNs are vulnerable to adversarial attacks, that are small perturbations embedded in an image. As a result, introduction of DNNs into safety-critical systems, such as autonomous vehicles, unmanned aerial vehicles or healthcare devices, would introduce very high risk of limiting their capabilities to recognize and interpret the environment in which they are used and therefore would lead to devastating consequences. Thus, robustness enhancement of DNNs by development of defense mechanisms is a matter of the utmost importance. In this paper, we evaluated a set of state-of-the-art denoising filters designed for impulsive noise removal as defensive solutions. The proposed methods are applied as a pre-processing step, in which the adversarial patterns in the source image are removed before performing classification task. As a result, the pre-processing defense block can be easily integrated with any type of classifier, without any knowledge about utilized training procedures or internal architecture of the model. Moreover, the evaluated filtering methods can be considered as universal defensive techniques, as they are completely unrelated with the internal aspects of the selected attack and can be applied against any type of adversarial threats. The experimental results obtained on German Traffic Sign Recognition Benchmark (GTSRB) have proven that the denoising filters provide high robustness against sparse adversarial attacks and do not significantly decrease the classification performance on non-altered data.
Deep learning has been widely applied in many computer vision tasks due to its impressive capability of automatic feature extraction and classification. Recently, deep neural networks have been used in image denosing, but most of the proposed approaches were designed for Gaussian noise suppression. Therefore, in this paper, we address the problem of impulsive noise reduction in color images using Denoising Convolutional Neural Networks (DnCNN). This network architecture utilizes the concept of deep residual learning and is trained to learn the residual image instead of the directly denoised one. Our preliminary results show that direct application of DnCNN allows to achieve significantly better results than the state-of-the-art filters designed for impulsive noise in color images.
A novel fast filtering technique for multiplicative noise removal in ultrasound images was presented in this paper. The proposed algorithm utilizes concept of digital paths created on the image grid presented in [1] adapted to the needs of multiplicative noise reduction. The new approach uses special type of digital paths so called EscapingPathModel and modified path length calculation based on topological as well as gray-scale distances. The experiments confirmed that the proposed algorithm achieves a comparable results with the existing state-of-the-art denoising schemes in suppressing multiplicative noise in ultrasound images.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.